Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    pointer and ptr

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    시
    1.12
    t
    1.09
    1
    1.09
     huts
    1.07
    č
    1.06
     neighborhoods
    1.02
     Y
    1.01
    지는
    1.00
     neighbourhoods
    1.00
    Implementation
    0.97
    POSITIVE LOGITS
    ți
    1.21
    י
    1.16
    ك
    1.12
    ла
    1.02
    िया
    1.02
    ول
    0.99
     диапа
    0.95
    <0xA5>
    0.94
    اً
    0.94
    но
    0.93
    Act Density 0.001%

    No Known Activations